Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1683 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.1781. Min Act: -0.0001

Data Index: 1114531 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0697. Min Act: -0.0001

Data Index: 1219344 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0352. Min Act: -0.0001

Data Index: 1007572 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0299. Min Act: -0.0001

Data Index: 1015571 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0149. Min Act: -0.0001

Data Index: 628932 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9992. Min Act: -0.0001

Data Index: 47913 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9946. Min Act: -0.0001

Data Index: 908332 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9473. Min Act: -0.0001

Data Index: 689795 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9439. Min Act: -0.0001

Data Index: 1298316 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9148. Min Act: -0.0001

Data Index: 867982 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9157. Min Act: -0.0001

Data Index: 473737 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9600. Min Act: -0.0001

Data Index: 682798 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9868. Min Act: -0.0001

Data Index: 982845 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8964. Min Act: -0.0001

Data Index: 494676 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9146. Min Act: -0.0001

Data Index: 1243854 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9438. Min Act: -0.0001

Data Index: 149560 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8878. Min Act: -0.0001

Data Index: 295125 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9288. Min Act: -0.0001

Data Index: 849150 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8907. Min Act: -0.0001

Data Index: 525902 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8514. Min Act: -0.0001

Data Index: 622375 (C4 (Web Text))

Max Activating Token Index: 593